US11842478B2 - Method and apparatus for automated adhesive wash-off quality control and root-cause analysis using artificial intelligence - Google Patents
Method and apparatus for automated adhesive wash-off quality control and root-cause analysis using artificial intelligence Download PDFInfo
- Publication number
- US11842478B2 US11842478B2 US17/061,463 US202017061463A US11842478B2 US 11842478 B2 US11842478 B2 US 11842478B2 US 202017061463 A US202017061463 A US 202017061463A US 11842478 B2 US11842478 B2 US 11842478B2
- Authority
- US
- United States
- Prior art keywords
- adhesive
- images
- wash
- covered areas
- assembly
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
- 239000000853 adhesive Substances 0.000 title claims abstract description 169
- 230000001070 adhesive effect Effects 0.000 title claims abstract description 169
- 238000000034 method Methods 0.000 title claims abstract description 93
- 238000013473 artificial intelligence Methods 0.000 title description 2
- 238000003908 quality control method Methods 0.000 title description 2
- 230000008569 process Effects 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 27
- 206010047571 Visual impairment Diseases 0.000 claims abstract description 15
- 238000000576 coating method Methods 0.000 claims description 43
- 238000004140 cleaning Methods 0.000 claims description 21
- 238000004519 manufacturing process Methods 0.000 claims description 17
- 238000003070 Statistical process control Methods 0.000 claims description 16
- 239000011324 bead Substances 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 6
- 239000007921 spray Substances 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 5
- 238000011144 upstream manufacturing Methods 0.000 claims description 2
- 239000007788 liquid Substances 0.000 claims 1
- 239000011248 coating agent Substances 0.000 description 26
- 238000001514 detection method Methods 0.000 description 10
- 238000000429 assembly Methods 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 6
- 230000007547 defect Effects 0.000 description 3
- 238000007598 dipping method Methods 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 239000003973 paint Substances 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000011109 contamination Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000004070 electrodeposition Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 229910052751 metal Inorganic materials 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 150000002739 metals Chemical class 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 229910019142 PO4 Inorganic materials 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000003287 bathing Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000007739 conversion coating Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- NBIIXXVUZAFLBC-UHFFFAOYSA-K phosphate Chemical compound [O-]P([O-])([O-])=O NBIIXXVUZAFLBC-UHFFFAOYSA-K 0.000 description 1
- 239000010452 phosphate Substances 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20072—Graph-based image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30156—Vehicle coating
Definitions
- the present disclosure relates to a system and a method for detecting faults in a vehicle manufacturing line.
- Adhesives have a wide range of applications within the automotive industry due to their ability to offer improved stiffness, fatigue durability, noise, vibration and harshness (NVH) and sealing.
- Adhesives are typically dispensed on the Body in White (BIW) sub-assemblies, which then go through a cleaning process, a paint pretreatment process, and an electrocoating (E-coating) process, before entering the baking oven for curing.
- the adhesive is uncured during the various processes before curing and may be prone to being washed off. Wash off in itself is not considered to be a major problem.
- the problem lies in what happens to the washed off adhesive beads or blobs. These blobs can easily be redeposited onto highly visible Class-A surfaces where they are cured within the bake oven. Such undesirable defects then have to be manually sanded and repaired leading to increased cost. Alternatively, these washed-off beads are removed from the bath via filtration leading to reduced filter life, compromised performance and increased maintenance costs.
- adhesive wash-off is inspected manually by examining the surfaces of the BIW for any visual adhesives.
- the manual inspection is time consuming and requires manpower.
- inspection or touching the vehicle is not allowed between stages prior to e-coat bake. As a result, the uncured adhesive beads cannot be removed prior to the e-coat bake oven.
- Vehicles are inspected after e-coat and prior to paint, but there is only a limited amount of time available to repair these defects due to line configurations.
- a method of detecting adhesive wash-off includes: capturing, by a vision system, before-images of adhesive-covered areas on an assembly bonded by an adhesive before a process; capturing, by the vision system, after-images of the adhesive-covered areas on the assembly after the process; and determining, by a data processing module, an occurrence of the adhesive wash-off based on a comparison between the before-images and the after-images.
- the data processing module is configured to determine the occurrence of the adhesive wash-off based on a change in size of the adhesive-covered areas in the before-images and the after-images, particularly when the change in size of the adhesive-covered areas exceeds a first threshold.
- the method further includes recording, by the data processing module, the number of occurrences of the adhesive wash-off and determining a root cause of the adhesive wash-off, particularly based on a statistical process control (SPC) chart, when the number of the occurrences of the adhesive wash-off exceeds a second threshold.
- SPC statistical process control
- the root cause is selected from a group consisting of misplacement of an adhesive bead during adhesive dispensing, oversized adhesive beads, adhesive viscosity, spray impingement pressure, water temperature, line speed, and down time.
- the process is a pretreatment process or an E-coating process.
- the method further includes: capturing, by the vision system, first images of the adhesive-covered areas before the pretreatment process; capturing, by the vision system, second images of the adhesive-covered areas after the pretreatment process and before the E-coating process; and capturing, by the vision system, third images of the adhesive-covered areas after the E-coating process.
- the first images are captured after a cleaning process.
- the method further includes: determining an occurrence of an adhesive squeeze-out based on a comparison between the first image and data stored in the data processing module and quantifying and normalizing, by the data processing module; the adhesive-covered areas to define a threshold number of acceptable adhesive wash-off; automatically sending an alert, by the data processing module, to an external device to report a change in wash-off performance when the threshold number of acceptable adhesive wash-off is exceeded.
- the alert includes a root cause of the adhesive wash-off.
- the assembly is a Body in White structure.
- the method further includes capturing, by the vision system, the before-images and the after-images of a left side, a right side, and a top side of the assembly.
- a method of detecting adhesive wash-off on a Body in White assembly includes: capturing, by a vision system, first images of adhesive-covered areas on the BIW assembly after a cleaning process and before a pretreatment process; capturing, by the vision system, second images of the adhesive-covered areas after the pretreatment process and before an E-coating process; capturing, by the vision system, third images of the adhesive-covered areas after the E-coating process; and comparing, by a data processing module, the second images against the first images, and the third images against the first images to determine an occurrence of the adhesive wash-off.
- a system for automatically detecting adhesive wash-off which includes a vision system configured to capture the before-images and the after-images of adhesive-covered areas, and a data processing module configured to compare the before-images and the after-images to determine the occurrence of the adhesive wash-off.
- FIG. 1 is a schematic diagram of a system for automatically detecting adhesive wash-off in a vehicle manufacturing line constructed in accordance with the teachings of the present disclosure
- FIG. 2 depicts a vehicle manufacturing line that incorporates a method of automatically detecting adhesive wash-off in accordance with the teachings of the present disclosure
- FIGS. 3 A to 3 D includes images of a plurality of adhesive-covered areas on a rear glass flange of a C-pillar ( FIGS. 3 A and 3 B ), a body-side door flange ( FIG. 3 C ), an A-pillar ( FIG. 3 D ) of the vehicle body showing these areas with or without out-of-specification (OOS) squeeze-out.
- OOS out-of-specification
- module may be replaced with the term “circuit”.
- the term “module” may refer to, be part of, or include: an Application Specific Integrated Circuit (ASIC); a digital, analog, or mixed analog/digital discrete circuit; a digital, analog, or mixed analog/digital integrated circuit; a combinational logic circuit; a field programmable gate array (FPGA); a processor circuit (shared, dedicated, or group) that executes code; a memory circuit (shared, dedicated, or group) that stores code executed by the processor circuit; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system-on-chip.
- ASIC Application Specific Integrated Circuit
- FPGA field programmable gate array
- the module may include one or more interface circuits.
- the interface circuits may include wired or wireless interfaces that are connected to a local area network (LAN), the Internet, a wide area network (WAN), or combinations thereof.
- LAN local area network
- WAN wide area network
- the functionality of any given module of the present disclosure may be distributed among multiple modules that are connected via interface circuits. For example, multiple modules may allow load balancing.
- a server (also known as remote, or cloud) module may accomplish some functionality on behalf of a client module.
- a system 10 for automatically detecting adhesive wash off in a vehicle manufacturing line constructed in accordance with the teachings of the present disclosure includes a vision system 12 and a data processing module 14 .
- the vision system 12 captures images of a vehicle body, particularly images of adhesive-covered areas on the vehicle body, at a plurality of locations between different processes along the vehicle manufacturing line.
- the images include first images 20 captured at a first location, second images 22 captured at a second location, and third images 24 captured at a third location.
- the first, second, and third images 20 , 22 , 24 may be taken from one or more of a left side, a right side, a top, underneath of the vehicle body, or may be taken from a particular location of interest.
- the cameras may capture images from underneath the vehicle or along the rockers to gain a more holistic perspective. It is conceivable that adhesive squeeze out from a rocker is likely to be redeposited onto a hood or roof during the e-coat dip stage as the vehicle is dragged into and out of the bath.
- the data processing module 14 includes an out-of-specification (OOS) squeeze-out determination module 30 , an adhesive wash-off determination module 32 , and a root cause analysis module 34 .
- OOS squeeze-out determination module 30 is configured to detect and determine at the first location an occurrence of OOS adhesive squeeze-out.
- the adhesive wash-off determination module 32 is configured to detect and determine at the second location and the third location an occurrence of adhesive wash-off.
- the root cause analysis module 34 is configured to perform a root cause analysis to determine a root cause of the OOS adhesive squeeze-out and a root cause of the adhesive wash-off.
- the root cause analysis module 34 includes various quality and statistics tools, such as root cause analysis algorithms, to determine the root causes of the OOS adhesive squeeze-out and adhesive wash-off.
- the data processing module 14 is configured to send an alert to an external device 36 , such as a server, when the number of the occurrences of OOS adhesive squeeze-out or the number of the occurrences of adhesive wash-off exceeds a threshold.
- an exemplary vehicle manufacturing line 40 that incorporates a method of automatically detecting adhesive wash-off in accordance with the teachings of the present disclosure may be a manufacturing line for manufacturing a vehicle body, such as a body in white (BIW) structure 46 .
- the vehicle manufacturing line 40 includes an adhesive dispensing line 44 for dispensing an adhesive on a plurality of components or sub-assemblies 42 to join the sub-assemblies 42 into a vehicle body, such as a BIW structure 46 , a cleaning and pretreatment line (“pretreatment line” hereinafter) 48 , an electrocoating (“E-coating”) and oven bake line (“E-coating line” hereinafter) 50 , in this order.
- pretreatment line an electrocoating
- E-coating line oven bake line
- the vision system 12 includes a plurality of cameras 52 located at a first location (A) at the end of the body assembly line right after the BIW structure 46 is completed and prior to the pretreatment line 48 , at a second location (B) between the pretreatment line 48 and the E-coating line 50 , and at a third location (C) between the E-coating line 50 and a final paint line.
- a first location A
- B second location
- C third location
- the vision system 12 includes a plurality of cameras 52 located at a first location (A) at the end of the body assembly line right after the BIW structure 46 is completed and prior to the pretreatment line 48
- B between the pretreatment line 48 and the E-coating line 50
- C third location between the E-coating line 50 and a final paint line.
- the plurality of cameras 52 capture first images 20 at the first location (A), the second images 22 at the second location (B), and the third images 24 at the third location (C).
- an adhesive is dispensed on a plurality of components or sub-assemblies 42 for bonding and joining the plurality of sub-assemblies 42 to form the BIW structure 46 .
- the BIW structure 46 goes through a pretreatment line 48 , which includes a spray cleaning process and a pretreatment dip process.
- a pretreatment dip process may involve applying a phosphate or conversion coating that helps obtain a high quality electrocoat finish in the subsequent E-coating process.
- the E-coating line 50 includes an E-coating process and a baking process in a bake oven.
- the BIW structure 46 is immersed in an electrocoat bath and coatings are applied to the pretreated surfaces of the BIW structure 46 .
- the coated BIW structure 46 is placed in the bake oven that cures and cross-links the E-coat.
- paintings including color coat and clearcoat are sequentially applied and cured in their respective ovens to maximize its performance properties.
- the adhesive is dispensed on a plurality of areas of the BIW structure 46 for bonding various components or sub-assemblies 42 of the BIW structure 46 , thereby forming a plurality of adhesive-covered areas 60 on the BIW structure 46 .
- the adhesive is properly applied, no or little adhesive is exposed on the surfaces of the BIW structure 46 .
- out-of-specification (OOS) adhesive squeeze-out 62 can be seen on the adhesive-covered areas 60 as circled by dashed lines in FIGS.
- Adhesive squeeze-out refers to the portion of the adhesive that is out of place, particularly on the surfaces of the BIW structure 46 . When the size or location of the adhesive squeeze-out is outside the acceptable range, the adhesive squeeze-out is out of specification and is prone to being washed-off in the subsequent cleaning, pretreatment and E-coating processes.
- FIG. 3 A shows a plurality of adhesive-covered areas on the rear glass flange between a C-pillar and a back panel (back wall of the cab behind the seat) without OOS adhesive squeeze out and with an OOS squeeze-out circled by dashed lines and indicated by reference number 62 .
- FIG. 3 B shows a plurality of OOS squeeze-out 62 on the rear glass flange.
- FIG. 3 C shows the adhesive-covered areas on a bodyside door flange with OOS squeeze-out 62 .
- FIG. 3 D shows the adhesive-covered areas along the A pillar with OOS squeeze out 62 .
- the plurality of cameras 52 take first images 20 of the adhesive-covered areas 52 at the first location (A) and send the first images 30 to the data processing module 14 for analysis.
- the first images 30 taken at the first location (A) right after the vehicle body is fully assembled provide baseline images of a fully assembled vehicle body, which can be used against a known standard.
- the OOS squeeze-out determination module 30 is configured to detect any out-of-specification (OOS) adhesive squeeze-out on the BIW structure 46 based on a comparison between the first images 20 and pre-stored data regarding an acceptable range of adhesive squeeze-out at the first location (A).
- OOS out-of-specification
- the OOS squeeze-out determination module 30 determines the occurrence of the OOS adhesive squeeze-out and records the occurrence of the OOS adhesive squeeze-out.
- the OOS squeeze-out determination module 30 may also send an alert to an external device 36 advising an operator to take action at this point, for example, to perform solvent-wiping excess adhesive squeeze-out.
- the OOS squeeze-out determination module 30 may identify the location of the OOS squeeze-out on the first images 20 by using a laser pointer for cleaning/removing the adhesive squeeze-out.
- the root cause analysis module 34 is activated to perform a root cause analysis to determine a root cause of the OOS adhesive squeeze-out.
- the OOS squeeze-out determination module 30 is also configured to quantify and normalize the adhesive-covered areas to define a threshold number for acceptable adhesive squeeze-out.
- the OOS squeeze-out determination module 30 may include a detection algorithm that can associate OOS squeeze-out number to the corresponding part ID, vehicle VIN number, and skid number in order to make the root-cause analysis process simpler.
- the BIW structure 46 is sent to the pretreatment line 48 .
- the adhesive-covered areas on the BIW structure 46 are prone to being washed off in the pretreatment line 48 due to, for example, high spray impingement pressure, increased pressure of deluge directed onto location of adhesive joint, increased temperature of water rinses and alkaline cleaners, increased static pressures encountered from immersion stages, and increased exposure time due to decrease in line speed. Therefore, the cameras 52 capture second images 22 of the adhesive-covered areas of the BIW structure 46 at the second location (B) after the BIW structure 46 exits the pretreatment line 48 and before entering the E-coating line 50 to identify any possible adhesive wash-off in the pretreatment line 48 .
- the adhesive wash-off determination module 32 compares the second images 22 against the first images 20 (for the corresponding sides) and determine whether adhesive wash-off has occurred based on the comparison between the first and second images 20 , 22 .
- the second images taken at location (B) show what adhesive has been removed during the pretreatment line 48 where high-pressure impingement nozzles and high temperature fluids are used to clean and prepare the surfaces for the E-coat dip.
- the adhesive wash-off determination module 32 compares the second images 22 against the first images 20 and determines where the adhesive has been removed and needs to be addressed upstream to prevent reoccurrence.
- the adhesive wash-off determination module 32 may implement a machine learning approach, training data set, and neural network framework to improve detection efficiency and performance. Training data set can be obtained from the previous images taken from the areas of interest and/or could be added in-line.
- the adhesive wash-off determination module 32 may compare at least one of the size, position, and displacement of the adhesive-covered area in the first and second images 20 , 22 depending where the adhesive-covered areas are on the components/sub-assemblies. For example, some adhesive-covered areas (such as a localized glob that has run down a flange) may have a relatively small area but pose a high risk of contamination, whereas another adhesive-covered areas may have a small uniform amount of squeeze-out along an edge of a joint which has a large cumulative area but pose little risk of contamination. When the change in size, position or displacement of the adhesive-covered area exceeds a first threshold, the adhesive wash-off determination module 32 determines the occurrence and severity of the adhesive wash-off.
- the adhesive wash-off determination module 32 may use different criteria for different adhesive-covered areas for determining the occurrence/severity of the adhesive wash-off.
- the root cause analysis module 34 is activated to analyze the root cause of the adhesive wash-off.
- the BIW structure 46 is sent to the E-coating line 50 .
- the BIW structure 46 is prone to being washed off due to, for example, high dipping temperature and processes. Therefore, the cameras 52 take third images 24 after the BIW structure 46 exits the E-coating line 50 .
- the adhesive wash-off determination module 32 compares the third images 24 against the first images 20 for the corresponding sides to determine whether adhesive wash-off has occurred in the E-coating line 50 .
- the third images 24 are taken after E-coat dip and bake to show if any adhesive is removed (compared to the second images and the first images) and also if any adhesive has been redeposited onto surface panels.
- the third images 24 are the final quality indicator and can show whether the wash-off problem has been solved as the system 10 of the present disclosure works backwards to improve the process.
- the adhesive wash-off determination module 32 may compare the size, location, or displacement (i.e. movement) of the adhesive-covered area in the first and third images 20 , 24 . When the change in size, location, or displacement of the adhesive-covered area exceeds a threshold, the adhesive wash-off determination module 32 may determine that adhesive wash-off has occurred or has increased the risk of wash-off in the E-coating line 50 . When a number of the occurrence of the wash-off exceeds a threshold, the root cause analysis module 34 is triggered to perform a root cause analysis for the adhesive wash-off in the E-coating line 50 . Similarly, the adhesive wash-off determination module 32 may be configured to quantify and normalize the adhesive-covered areas to define threshold values for the maximum allowed adhesive wash-off at the second location (B) and the third location (C), respectively.
- the ultimate goal would be zero wash-off.
- the compilation of the first, second and third images 20 , 22 , 24 allows the system 10 of the present disclosure to track where the problem occurs along with quantifying the improvement.
- Using the system 10 of the present disclosure would “drill down” into the cause and take action to remedy the problem, as opposed to prior art devices or methods where an operator is aware of the results at the end of e-coat bake but has little understanding as to how or when these problems occur.
- an operator can only see adhesive related issues at the end of the E-coat line and then go crawling over the body to point out where they see adhesive and believe that this is the root cause.
- the root-cause analysis module 34 includes a machine learning module to analyze the factors related to the OOS squeeze-out, or adhesive wash-off when the number of the occurrences of OOS squeeze-out or the adhesive wash-off exceeds a threshold.
- the root-cause analysis module 34 may “back-track” and determine the root-cause of OOS adhesive squeeze out through artificial intelligence (AI) and machine learning (ML) algorithms by analyzing the factors related to the OOS adhesive squeeze-out or the adhesive wash-off.
- AI artificial intelligence
- ML machine learning
- the root-cause analysis module 34 analyzes the time series data for the critical factors/parameters affecting adhesive dispensing quality and adhesive wash-off performance and determines if there is any deviation from statistical process control (SPC) charts.
- SPC is a method of controlling quality of products being produced by employing statistical methods to monitor and control a process.
- Each of the adhesive dispensing line 44 , the pretreatment line 48 , and the E-coating line 50 may have its own SPC chart for controlling its process.
- the SPC chart for the adhesive dispensing line 44 may include statistical data regarding the adhesive dispensing data/parameters, such as a refill time and/or shot meter back pressure.
- the SPC chart for the pretreatment process may include statistical data regarding the pretreatment process data/parameters, such as the spraying pressure, water temperature, etc.
- the SPC chart for the E-coating process may include statistical data regarding the E-coating data/parameters, such as dipping temperature and dipping pressure, among others.
- the root-cause analysis module 34 can determine the root cause of the 00 S squeeze out or the adhesive wash-off based on such deviation.
- the factors relating to 00 S squeeze out may include, but not be limited to, improper adhesive viscosity, improper bead size, and bead misplacement.
- the adhesive viscosity can be obtained from the quality control data provided by adhesive suppliers.
- dispensing data such as refill time and/or shot meter back pressure can be correlated to the adhesive viscosity for each dispensed shot.
- the misplacement of adhesive bead can be detected by comparing the amount of adhesive squeeze out at the first location with that of previous vehicles, if no significant viscosity change was reported for the adhesive dispensed on the same part ID.
- the locations of possible adhesive wash-off in the subsequent E-coating process can be detected and the possible wash-off problem can be solved as early as possible.
- the root-cause analysis module 34 may check the various parameters in the adhesive dispensing line 44 against the SPC chart to determine whether any of the operating parameters is outside the upper limits and the lower limits based on the SPC chart, thereby determining the root cause of the 00 S squeeze out.
- the root-cause analysis module 34 may check the various parameters in the pretreatment line 48 and the E-coating line 50 against their respective SPC to determine whether any of the operating parameters is outside the upper limits and the lower limits based on their respective SPC chart, thereby determining the root cause of the adhesive wash-off in the pretreatment line 48 and the E-coating line 50 , respectively.
- the system and method of the present disclosure can automatically monitor and detect the surfaces of the BIW structure to identify any OOS adhesive squeeze-out right after the BIW structure is assembled and before the cleaning and pretreatment line, and any adhesive wash-off in the cleaning and pretreatment line and the E-coating and oven bake line.
- the data processing module 14 is configured to receive first, second and third images 20 , 22 , 24 from the vision system 12 at different locations along the vehicle manufacturing line and automatically identify the occurrence of OOS adhesive squeeze-out and adhesive wash-off, its location and displacement based on the first, second and third images 20 , 22 , 24 .
- the data processing module 14 may be integrated in a computing device, such as a laptop computer, a desktop computer, a server, a network computer, a personal digital assistant (PDA), a smart phone, and a tablet.
- PDA personal digital assistant
- the system and method have the advantages of performing automatic wash-off detection and root-cause analysis without human interaction, thereby saving manhours and avoiding prolonged manual root-cause analysis.
- the detection of OOS adhesive squeeze out, the detection of adhesive wash-off, and the root cause analysis are performed automatically through an advanced detection algorithm that can associate wash-off performance number to the corresponding part ID, vehicle VIN number, and skid number in order to make the detection and the root-cause analysis process simpler.
- the system and the method can save manufacturing and maintenance costs due to early detection of the adhesive wash-off. Due to early detection and root-cause analysis, the occurrence of adhesive wash-off in the bath can be reduced and significant amount of adhesive deposition in the bath and on the filter can be avoided, while reducing coating quality issues through early detection and root-cause analysis. No significant investment (e.g. minimum three cameras and a data processing module) is required compared to the cumulative savings due to reduced maintenance and quality issues.
Abstract
Description
Claims (20)
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/061,463 US11842478B2 (en) | 2020-10-01 | 2020-10-01 | Method and apparatus for automated adhesive wash-off quality control and root-cause analysis using artificial intelligence |
DE102021125460.4A DE102021125460A1 (en) | 2020-10-01 | 2021-09-30 | METHOD AND DEVICE FOR AUTOMATED ADHESIVE WASH-OFF QUALITY CONTROL AND ROOT CAUSE ANALYSIS USING ARTIFICIAL INTELLIGENCE |
CN202111173776.XA CN114264650A (en) | 2020-10-01 | 2021-10-08 | Method and apparatus for automatic adhesive flushing quality control |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/061,463 US11842478B2 (en) | 2020-10-01 | 2020-10-01 | Method and apparatus for automated adhesive wash-off quality control and root-cause analysis using artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
US20220108432A1 US20220108432A1 (en) | 2022-04-07 |
US11842478B2 true US11842478B2 (en) | 2023-12-12 |
Family
ID=80738527
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/061,463 Active 2041-04-06 US11842478B2 (en) | 2020-10-01 | 2020-10-01 | Method and apparatus for automated adhesive wash-off quality control and root-cause analysis using artificial intelligence |
Country Status (3)
Country | Link |
---|---|
US (1) | US11842478B2 (en) |
CN (1) | CN114264650A (en) |
DE (1) | DE102021125460A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11842478B2 (en) * | 2020-10-01 | 2023-12-12 | Ford Global Technologies, Llc | Method and apparatus for automated adhesive wash-off quality control and root-cause analysis using artificial intelligence |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6687402B1 (en) * | 1998-12-18 | 2004-02-03 | Cognex Corporation | Machine vision methods and systems for boundary feature comparison of patterns and images |
US20040081347A1 (en) * | 2001-01-19 | 2004-04-29 | Christian Bernatek | Method for determining and evaluating defects in a sample surface |
DE102004008300A1 (en) | 2004-02-20 | 2005-09-01 | Daimlerchrysler Ag | Cleaning method for a motor vehicle's/car's raw bodywork carcass uses an optical image-capture system and a pattern-recognition device to scan for traces of adhesive and to detect impurities |
US20100193974A1 (en) * | 2008-04-23 | 2010-08-05 | Au Optronics Corporation | Substrate with Check Mark and Method of Inspecting Position Accuracy of Conductive Glue Dispensed on the Substrate |
US8073239B1 (en) * | 2008-09-24 | 2011-12-06 | Valco Cincinnati, Inc. | Error detection system for verifying the construction of paper boxes |
US20130231769A1 (en) * | 2012-03-01 | 2013-09-05 | Taiwan Semiconductor Manufacturing Company, Ltd. | Defect Management Systems and Methods |
GB2515115A (en) | 2013-06-14 | 2014-12-17 | Warwick Analytical Software Ltd | Early Warning and Prevention System |
US20160350909A1 (en) * | 2015-05-28 | 2016-12-01 | Jabil Circuit, Inc. | System, apparatus and method for dispensed adhesive material inspection |
US20170206468A1 (en) | 2016-01-20 | 2017-07-20 | Robert Bosch Gmbh | Value addition dependent data mining techniques for assembly lines |
US20180189940A1 (en) * | 2016-12-30 | 2018-07-05 | Hongfujin Precision Electronics (Zhengzhou) Co., Ltd. | Electronic device and method for checking dispensing of glue in relation to circuit board |
US20190300759A1 (en) * | 2018-03-30 | 2019-10-03 | The Boeing Company | Compositions and methods for probing adhesive interfaces |
US20200151861A1 (en) * | 2018-11-13 | 2020-05-14 | Rivian Ip Holdings, Llc | Image analysis of applied adhesive with fluorescence enhancement |
CN114264650A (en) * | 2020-10-01 | 2022-04-01 | 福特全球技术公司 | Method and apparatus for automatic adhesive flushing quality control |
-
2020
- 2020-10-01 US US17/061,463 patent/US11842478B2/en active Active
-
2021
- 2021-09-30 DE DE102021125460.4A patent/DE102021125460A1/en active Pending
- 2021-10-08 CN CN202111173776.XA patent/CN114264650A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6687402B1 (en) * | 1998-12-18 | 2004-02-03 | Cognex Corporation | Machine vision methods and systems for boundary feature comparison of patterns and images |
US20040081347A1 (en) * | 2001-01-19 | 2004-04-29 | Christian Bernatek | Method for determining and evaluating defects in a sample surface |
DE102004008300A1 (en) | 2004-02-20 | 2005-09-01 | Daimlerchrysler Ag | Cleaning method for a motor vehicle's/car's raw bodywork carcass uses an optical image-capture system and a pattern-recognition device to scan for traces of adhesive and to detect impurities |
US20100193974A1 (en) * | 2008-04-23 | 2010-08-05 | Au Optronics Corporation | Substrate with Check Mark and Method of Inspecting Position Accuracy of Conductive Glue Dispensed on the Substrate |
US8073239B1 (en) * | 2008-09-24 | 2011-12-06 | Valco Cincinnati, Inc. | Error detection system for verifying the construction of paper boxes |
US20130231769A1 (en) * | 2012-03-01 | 2013-09-05 | Taiwan Semiconductor Manufacturing Company, Ltd. | Defect Management Systems and Methods |
GB2515115A (en) | 2013-06-14 | 2014-12-17 | Warwick Analytical Software Ltd | Early Warning and Prevention System |
US20160350909A1 (en) * | 2015-05-28 | 2016-12-01 | Jabil Circuit, Inc. | System, apparatus and method for dispensed adhesive material inspection |
US20170206468A1 (en) | 2016-01-20 | 2017-07-20 | Robert Bosch Gmbh | Value addition dependent data mining techniques for assembly lines |
US20180189940A1 (en) * | 2016-12-30 | 2018-07-05 | Hongfujin Precision Electronics (Zhengzhou) Co., Ltd. | Electronic device and method for checking dispensing of glue in relation to circuit board |
US20190300759A1 (en) * | 2018-03-30 | 2019-10-03 | The Boeing Company | Compositions and methods for probing adhesive interfaces |
US20200151861A1 (en) * | 2018-11-13 | 2020-05-14 | Rivian Ip Holdings, Llc | Image analysis of applied adhesive with fluorescence enhancement |
CN114264650A (en) * | 2020-10-01 | 2022-04-01 | 福特全球技术公司 | Method and apparatus for automatic adhesive flushing quality control |
Non-Patent Citations (1)
Title |
---|
Geary, Best Approach to Adhesion Failure Root-Cause Analysis, BTG Labs blogpost, 2020, pp. 1-9. |
Also Published As
Publication number | Publication date |
---|---|
DE102021125460A1 (en) | 2022-04-07 |
US20220108432A1 (en) | 2022-04-07 |
CN114264650A (en) | 2022-04-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Priya et al. | Defect analysis and lean six sigma implementation experience in an automotive assembly line | |
JP5802326B2 (en) | Color harmony using process and environmental feedback | |
US11842478B2 (en) | Method and apparatus for automated adhesive wash-off quality control and root-cause analysis using artificial intelligence | |
US11155908B2 (en) | Method and system for using an irreversible thermo-chromatic indicator for quality assurance of a part subjected to heat treating | |
CN111822286A (en) | Spraying process for gasoline generator set | |
EP4324889A2 (en) | METHOD FOR ANALYSING QUALITY DEFECTS	[ | |
Altinisik et al. | The seven-step failure diagnosis in automotive industry | |
CN112373601A (en) | Energy-saving automobile assembly process | |
KR20160139866A (en) | The system for embrocating primer and for inspecting condition of primer embrocation | |
CN115266161A (en) | Pollution detection method and device for vehicle spraying machine | |
CN112658662B (en) | Equipment assembling method and locomotive bogie | |
JPH06148090A (en) | Painting inspection information analyzer | |
CN114118198A (en) | Method and device for determining defects in a surface modification method | |
US20240124079A1 (en) | Method and system of automated vehicle body routing system employing predicted vehicle body imperfections and vision detection system | |
Li et al. | Application of lean manufacturing in product safety | |
US10416061B2 (en) | Blank washer inspection system | |
Ju et al. | Modeling quality propagation in automotive paint shops: An application study | |
JP7411622B2 (en) | Paint diagnosis system, paint diagnosis method | |
CN116128878B (en) | Intelligent spraying track generation method and system based on automobile sheet metal | |
DE10326604A1 (en) | Control device for an atomizer for a spraying robot in a paint line especially for motor vehicles has scanner automatic control and transport system with separating walls | |
US20170342587A1 (en) | Object processing by conversion coating | |
JPS591730Y2 (en) | Pretreatment equipment for painting | |
JPS5847232B2 (en) | Pretreatment method for painting | |
Dössel | In‐Plant Repairs | |
CN114174157A (en) | Method for producing an assembly |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
AS | Assignment |
Owner name: FORD GLOBAL TECHNOLOGIES, LLC, MICHIGAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:WELLER, CHRISTOPHER;HILL, DAVID JOHN;MOJDEHI, AHMAD;SIGNING DATES FROM 20200930 TO 20201001;REEL/FRAME:054863/0408 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: FINAL REJECTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT RECEIVED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |